An autonomous route planning method for unmanned aerial vehicles
Through the dynamic adjustment of drone mission planning and sensor information, the problem of insufficient autonomy and adaptability of drones in path planning in complex environments is solved, and the drone's autonomous obstacle avoidance and threat avoidance capabilities are improved, so as to achieve Reduced resource consumption and improved computing efficiency.
Patent Information
- Application Number
- CN202210722866.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-24
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-06-24
AI Technical Summary
The existing drone path planning technology cannot quickly respond to multiple emergencies and autonomous task planning in complex environments, lacks adaptability, and cannot effectively improve the survivability and mission efficiency of drones in complex environments.
By using information from drone mission planning, navigation and positioning sensors and environment perception sensors, combined with prior information, dynamically adjust the drone mission path, set obstacle avoidance radius and threat impact factors, evaluate and optimize path priorities in real time, and determine the most Optimize the path.
It has achieved the improvement of the ability of drones to avoid obstacles and threats in complex environments, reduced resource consumption, and has a small computing volume and good practical value.
Smart Images

Figure CN114935945B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to an autonomous route planning method suitable for unmanned aerial vehicles, and belongs to the field of intelligent cooperative control of unmanned aerial vehicles. Background Art
[0002] Drones often face complex and ever-changing environments, such as the emergence of new targets and new threats, interceptions on the original track or the existence of unknown obstacles, and small time delays in complex environments. Therefore, autonomous and fast track planning is crucial for drones.
[0003] Existing path planning technology cannot solve the problem of rapid and multiple sudden threats, and does not have autonomous task planning and the ability to adapt when the system environment changes. UAV intelligent control technology is the future development direction of UAV control. It uses artificial intelligence related technologies to integrate and reconstruct the functions of UAV ground control stations, and builds a simple, efficient, flexible, configurable and autonomous UAV intelligent path planning system for UAVs, so as to improve the survivability of UAVs and enhance mission efficiency.
[0004] UAV intelligent path planning means that if the system allows, users can specify the degree of autonomous control in the system, and can change it from no to near autonomy, or completely autonomous, so that the UAV can autonomously determine the flight path in harsh environments based on mission planning, autonomous navigation and positioning, and environmental perception. However, there is currently a lack of relevant mature technologies in autonomous route planning for UAVs. Summary of the invention
[0005] In view of this, the present invention proposes an autonomous route planning method suitable for UAVs. The method can realize autonomous planning of UAV mission paths through continuous dynamic adjustment with the assistance of prior information based on sensor information obtained by UAV mission planning, navigation positioning sensors and environmental perception sensors.
[0006] In order to achieve the above object, the technical solution adopted by the present invention is:
[0007] An autonomous route planning method for a UAV comprises the following steps:
[0008] (1) Plan the current path according to the UAV mission, initialize parameters, and determine the current status of various sensors; the various sensors include environmental perception sensors, navigation and positioning sensors, and carrier status sensors; at time k, the environmental perception sensors output surrounding obstacle information a k , Electromagnetic environment information b k ; Navigation and positioning sensors output current location information q k ; The carrier state sensor outputs the current speed v of the dronek ;
[0009] (2) According to the current speed v of the drone k and path planning decision detection time t v Set the obstacle avoidance radius R of the drone v , v k t v <R v ;
[0010] (3) According to the mission and navigation positioning information of the UAV, the feasible path direction of the current UAV is divided into M paths, and the priority coefficient vector ρ of the M paths is determined according to the optimal path principle. k =[ρ k1 ,…,ρ ki ,…,ρ kM ], where i = 1,…,M, λ ki is the task completion quality coefficient of the ith route at time k, l ki is the destination q of the i-th route at time k e The distance, L k Arriving at destination q at time k e The shortest distance;
[0011] (4) Determine whether there are obstacles on the M paths based on the anti-collision sensor. If the obstacle is at a distance d ki ≤R v , then the path is not feasible and will be eliminated in path planning; if R v <d ki ≤μR v , 1<μ<10, then reduce the priority of the path, that is, ρ ki =ξd ki ρ ki , where ξ is the obstacle avoidance priority adjustment coefficient, and its value range is If d ki ≥μR v , then the path is considered feasible and the path priority coefficient is not adjusted; the remaining M1 paths are combined into a new path priority coefficient vector Where j = 1,…,M1;
[0012] (5) Determine whether there is a threat on the remaining M1 paths based on the electromagnetic environment perception sensor; assume that the distance at which the drone can detect the threat is R D , R D >>R v , the distance threatening the drone is R J , the threat impact factors of M1 paths are Assume that the starting and ending positions of the affected range of each path are Then the impact of the threat on the jth path on the UAV is Among them, O j is any point on the jth path, δ j is the path influence coefficient, 0<δ j ≤J / J0, J is the interference power reaching the UAV, and J0 is the minimum power that can interfere with the UAV;
[0013] Adjust the priorities of the remaining M1 paths, that is, Get the path priority coefficient vector with threat impact added
[0014] (6) Comparison of ρ″ kT The priority coefficients of the M1 paths are calculated, and the maximum value is found. The path corresponding to the maximum value is the optimal path for the drone at the current moment.
[0015] (7) When the environment changes or exceeds the current planned stable area, that is, d F ≥R v When F In order to plan the flight distance based on the current path, return to step (2) to perform path planning.
[0016] The beneficial effects of the present invention are:
[0017] 1. The present invention perceives the status information of each sensor in real time, determines the current feasible path in real time, evaluates the priority of the current feasible path, and makes adjustments to the route planning in real time.
[0018] 2. The present invention can effectively improve the drone's ability to autonomously avoid obstacles and evade threats and attacks, and reduce the resource consumption of the drone during mission execution.
[0019] 3. The method of the present invention has a small amount of calculation, takes comprehensive factors into consideration, and has good practical value. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 The figure is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION
[0021] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0022] An autonomous route planning method suitable for unmanned aerial vehicles (UAVs). The method realizes autonomous planning of the UAV mission path dynamically through the assistance of prior information and continuous judgment and adjustment based on the sensor information obtained by the UAV mission planning, navigation and positioning sensors and environmental perception sensors.
[0023] like Figure 1 As shown, the method comprises the following steps:
[0024] (1) Plan the current path according to the UAV mission, initialize parameters, and determine the current status of various sensors; the various sensors include environmental perception sensors, navigation and positioning sensors, and carrier status sensors; at time k, the environmental perception sensors output surrounding obstacle information a k , Electromagnetic environment information b k ; Navigation and positioning sensors output current location information q k ; The carrier state sensor outputs the current speed v of the drone k ;
[0025] (2) According to the current speed v of the drone k and path planning decision detection time t v Set the obstacle avoidance radius R of the drone v , v k t v <R v ;
[0026] (3) According to the mission and navigation positioning information of the UAV, the feasible path direction of the current UAV is divided into M paths, and the priority coefficient vector ρ of the M paths is determined according to the optimal path principle. k =[ρ k1 ,…,ρ ki ,…,ρ kM ], where i = 1,…,M, λ ki is the task completion quality coefficient of the ith route at time k, l ki is the destination q of the i-th route at time k e The distance, L k Arriving at destination q at time k e The shortest distance;
[0027] (4) Determine whether there are obstacles on the M paths based on the anti-collision sensor. If the obstacle is at a distance d ki ≤R v , then the path is not feasible and will be eliminated in path planning; if R v <d ki ≤μR v , 1<μ<10, then reduce the priority of the path, that is, ρ ki =ξd ki ρ ki , where ξ is the obstacle avoidance priority adjustment coefficient, and its value range is If d ki ≥μR v, then the path is considered feasible and the path priority coefficient is not adjusted; the remaining M1 paths are combined into a new path priority coefficient vector Where j = 1,…,M1;
[0028] (5) Determine whether there is a threat on the remaining M1 paths based on the electromagnetic environment perception sensor; assume that the distance at which the drone can detect the threat is R D , R D >>R v , the distance threatening the drone is R J , the threat impact factors of M1 paths are Assume that the starting and ending positions of the affected range of each path are Then the impact of the threat on the jth path on the UAV is Among them, O j is any point on the jth path, δ j is the path influence coefficient, 0<δ j ≤J / J0, J is the interference power reaching the UAV, and J0 is the minimum power that can interfere with the UAV;
[0029] Adjust the priorities of the remaining M1 paths, that is, Get the path priority coefficient vector with threat impact added
[0030] (6) Comparison of ρ″ kT The priority coefficients of the M1 paths are calculated, and the maximum value is found. The path corresponding to the maximum value is the optimal path for the drone at the current moment.
[0031] (7) When the environment changes or exceeds the current planned stable area, that is, d F ≥R v When F In order to plan the flight distance based on the current path, return to step (2) to perform path planning.
[0032] In summary, the present invention can adjust the priority of feasible paths of the UAV according to the mission requirements of the UAV, the sensor information obtained by the navigation positioning sensor and the environmental perception sensor, and dynamically judge the degree of threat of obstacles and interference strikes around the UAV, determine the optimal path in the current environment, and realize autonomous navigation. The present invention improves the autonomous decision-making flight capability and working reliability of the UAV in complex environments, and has the characteristics of simple implementation, small calculation amount and high autonomous control level.
Claims
1. An autonomous route planning method suitable for unmanned aerial vehicles, characterized in that: The following steps are involved: (1) Plan the current path according to the UAV mission, initialize parameters, and determine the current status of various sensors; the various sensors include environmental perception sensors, navigation and positioning sensors, and carrier status sensors; at time k, the environmental perception sensors output surrounding obstacle information a k , Electromagnetic environment information b k ; Navigation and positioning sensors output current location information q k ; The carrier state sensor outputs the current speed v of the drone k ; (2) According to the current speed v of the drone k and path planning decision detection time t v Set the obstacle avoidance radius R of the drone v , v k t v <R v ; (3) According to the mission and navigation positioning information of the UAV, the feasible path direction of the current UAV is divided into M paths, and the priority coefficient vector ρ of the M paths is determined according to the optimal path principle. k =[ρ k1 ,…,ρ ki ,…,ρ kM ], where i = 1,…,M, λ ki is the task completion quality coefficient of the ith route at time k, l ki is the destination q of the i-th route at time k e The distance, L k Arriving at destination q at time k e The shortest distance; (4) Determine whether there are obstacles on the M paths based on the anti-collision sensor. If the obstacle is at a distance d ki ≤R v , then the path is not feasible and will be eliminated in path planning; if R v <d ki ≤μR v , 1<μ<10, then reduce the priority of the path, that is, ρ ki =ξd ki ρ ki , where ξ is the obstacle avoidance priority adjustment coefficient, and its value range is If d ki ≥μR v , then the path is considered feasible and the path priority coefficient is not adjusted; the remaining M1 paths are combined into a new path priority coefficient vector Where j = 1,…,M1; (5) Determine whether there is a threat on the remaining M1 paths based on the electromagnetic environment perception sensor; assume that the distance at which the drone can detect the threat is R D , R D >>R v , the distance threatening the drone is R J , the threat impact factors of M1 paths are Assume that the starting and ending positions of the affected range of each path are Then the impact of the threat on the jth path on the UAV is Among them, O j is any point on the jth path, δ j is the path influence coefficient, 0<δ j ≤J / J0, J is the interference power reaching the UAV, and J0 is the minimum power that can interfere with the UAV; Adjust the priorities of the remaining M1 paths, that is, Get the path priority coefficient vector with threat impact added (6) Comparison of ρ″ kT The priority coefficients of the M1 paths are calculated, and the maximum value is found. The path corresponding to the maximum value is the optimal path for the drone at the current moment. (7) When the environment changes or exceeds the current planned stable area, that is, d F ≥R v When F In order to plan the flight distance based on the current path, return to step (2) to perform path planning.
